A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913653305901056 |
|---|---|
| author | Wang, Huandong Fu, Wenjie Tang, Yingzhou Chen, Zhilong Huang, Yuxi Piao, Jinghua Gao, Chen Xu, Fengli Jiang, Tao Li, Yong |
| author_facet | Wang, Huandong Fu, Wenjie Tang, Yingzhou Chen, Zhilong Huang, Yuxi Piao, Jinghua Gao, Chen Xu, Fengli Jiang, Tao Li, Yong |
| contents | While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy leakage, hallucinated outputs, and value misalignment, and can be maliciously used for generating toxic content and unethical purposes after been jailbroken. Therefore, in this survey, we present a comprehensive review of recent advancements aimed at mitigating these issues, organized across the four phases of LLM development and usage: data collecting and pre-training, fine-tuning and alignment, prompting and reasoning, and post-processing and auditing. We elaborate on the recent advances for enhancing the performance of LLMs in terms of privacy protection, hallucination reduction, value alignment, toxicity elimination, and jailbreak defenses. In contrast to previous surveys that focus on a single dimension of responsible LLMs, this survey presents a unified framework that encompasses these diverse dimensions, providing a comprehensive view of enhancing LLMs to better serve real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09431 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy Wang, Huandong Fu, Wenjie Tang, Yingzhou Chen, Zhilong Huang, Yuxi Piao, Jinghua Gao, Chen Xu, Fengli Jiang, Tao Li, Yong Artificial Intelligence Computation and Language Cryptography and Security Computers and Society While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy leakage, hallucinated outputs, and value misalignment, and can be maliciously used for generating toxic content and unethical purposes after been jailbroken. Therefore, in this survey, we present a comprehensive review of recent advancements aimed at mitigating these issues, organized across the four phases of LLM development and usage: data collecting and pre-training, fine-tuning and alignment, prompting and reasoning, and post-processing and auditing. We elaborate on the recent advances for enhancing the performance of LLMs in terms of privacy protection, hallucination reduction, value alignment, toxicity elimination, and jailbreak defenses. In contrast to previous surveys that focus on a single dimension of responsible LLMs, this survey presents a unified framework that encompasses these diverse dimensions, providing a comprehensive view of enhancing LLMs to better serve real-world applications. |
| title | A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy |
| topic | Artificial Intelligence Computation and Language Cryptography and Security Computers and Society |
| url | https://arxiv.org/abs/2501.09431 |